Results 1 - 10 of 724

Gradient-based learning applied to document recognition

by Yann Lecun, Léon Bottou, Yoshua Bengio, Patrick Haffner - Proceedings of the IEEE , 1998
"... Multilayer neural networks trained with the back-propagation algorithm constitute the best example of a successful gradientbased learning technique. Given an appropriate network architecture, gradient-based learning algorithms can be used to synthesize a complex decision surface that can classify hi ..."
Abstract - Cited by 1533 (84 self) - Add to MetaCart
high-dimensional patterns, such as handwritten characters, with minimal preprocessing. This paper reviews various methods applied to handwritten character recognition and compares them on a standard handwritten digit recognition task. Convolutional neural networks, which are specifically designed

Handwritten Digit Recognition with a Back-Propagation Network

by Le Cun, B. Boser, J. S. Denker, D. Henderson, R. E. Howard, W. Hubbard, L. D. Jackel - Advances in Neural Information Processing Systems , 1990
"... We present an application of back-propagation networks to handwritten digit recognition. Minimal preprocessing of the data was required, but architecture of the network was highly constrained and specifically designed for the task. The input of the network consists of normalized images of isolated d ..."
Abstract - Cited by 285 (21 self) - Add to MetaCart
We present an application of back-propagation networks to handwritten digit recognition. Minimal preprocessing of the data was required, but architecture of the network was highly constrained and specifically designed for the task. The input of the network consists of normalized images of isolated

Optimizing landmark-based routing and preprocessing

by Alexandros Efentakis, Dieter Pfoser - In Proceedings of the 6th ACM SIGSPATIAL International Workshop on Computational Transportation Science, IWCTS ’13 , 2013
"... Many acceleration techniques exist for the single-pair shortest path problem on road networks. Most of them have been significantly improved over the years to achieve faster preprocessing times and superior performance. In this spirit, our current work significantly improves the classic ALT (A ∗ + L ..."
Abstract - Cited by 3 (3 self) - Add to MetaCart
∗ + Landmarks + Triangle equality) algorithm. By carefully optimizing both preprocessing and query phases, we managed to effectively minimize preprocessing time to a few seconds, making the ALT algorithm also suitable for dynamic scenarios, i.e., road networks with changing edge weights due to traffic updates

On Minimizing the Numbers of ADMs -- Better Bounds for an Algorithm with Preprocessing

by Su-xia Cui, et al. , 2008
"... Minimizing the number of electronic switches in optical networks is a main research topic in recent studies. In such networks we assign colors to a given set of lightpaths. Thus the lightpaths are partitioned into cycles and paths, and the switching cost is minimized when the number of paths is mi ..."
Abstract - Add to MetaCart
Minimizing the number of electronic switches in optical networks is a main research topic in recent studies. In such networks we assign colors to a given set of lightpaths. Thus the lightpaths are partitioned into cycles and paths, and the switching cost is minimized when the number of paths

Efficient learning of sparse representations with an energy-based model

by Marc'Aurelio Ranzato, Christopher Poultney, Sumit Chopra, Yann Lecun - ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS (NIPS 2006 , 2006
"... We describe a novel unsupervised method for learning sparse, overcomplete features. The model uses a linear encoder, and a linear decoder preceded by a sparsifying non-linearity that turns a code vector into a quasi-binary sparse code vector. Given an input, the optimal code minimizes the distance b ..."
Abstract - Cited by 219 (15 self) - Add to MetaCart
We describe a novel unsupervised method for learning sparse, overcomplete features. The model uses a linear encoder, and a linear decoder preceded by a sparsifying non-linearity that turns a code vector into a quasi-binary sparse code vector. Given an input, the optimal code minimizes the distance

Signal Preprocessing of Multiwavelets

by T. R. Downie , 1998
"... Orthogonal wavelet bases have been developed using multiple mother wavelet functions. Applying the discrete multiwavelet transform requires the input data to be preprocessed to obtain a more economical decomposition. Four characteristics of a preprocessing method are presented: length, degree, ortho ..."
Abstract - Cited by 1 (1 self) - Add to MetaCart
Orthogonal wavelet bases have been developed using multiple mother wavelet functions. Applying the discrete multiwavelet transform requires the input data to be preprocessed to obtain a more economical decomposition. Four characteristics of a preprocessing method are presented: length, degree

Formula Preprocessing in MUS Extraction

by Anton Belov, Matti Järvisalo, Joao Marques-silva , 2013
"... Efficient algorithms for extracting minimally unsatisfiable subformulas (MUSes) of Boolean formulas find a wide range of applications in the analysis of systems, e.g., hardware and software bounded model checking. In this paper we study the applicability of preprocessing techniques for Boolean sati ..."
Abstract - Cited by 3 (0 self) - Add to MetaCart
Efficient algorithms for extracting minimally unsatisfiable subformulas (MUSes) of Boolean formulas find a wide range of applications in the analysis of systems, e.g., hardware and software bounded model checking. In this paper we study the applicability of preprocessing techniques for Boolean

Pre-Processing MRSes

by Tore Bruland
"... We are in the process of creating a pipeline for our HPSG grammar for Norwegian (NorSource). NorSource uses the meaning representation Minimal Recursion Semantics (MRS). We present a step for validating an MRS and a step for pre-processing an MRS. The pre-processing step connects our MRS elements to ..."
Abstract - Add to MetaCart
We are in the process of creating a pipeline for our HPSG grammar for Norwegian (NorSource). NorSource uses the meaning representation Minimal Recursion Semantics (MRS). We present a step for validating an MRS and a step for pre-processing an MRS. The pre-processing step connects our MRS elements

Video Preprocessing For Audiovisual Indexing

by Alberto Albiol Politechnic, Alberto Albiol - in Proc. IEEE Intl. Conf. on Acoustics, Speech, and Signal Processing (ICASSP’02), Vol.4, IV-3636 -IV-3639. LYU0302 : PVCAIS – Personal VideoConference Archives Indexing System Page 66 of Computer Science and Engineering, CUHK 2003-2004 Final Year Projec , 2002
"... In this paper we address the problem of reducing the amount of data to be analyzed when indexing audiovisual secuences. The reduction is based in selecting those parts of the video sequence where it is likely that there is a face talking. This can be useful since usually this kind of scenes contain ..."
Abstract - Add to MetaCart
important and reusable information such as interviews. The proposed technique is based on our a priori knowledge of the editing techniques used in news sequences. The results show that with this algorithm it is possible to discard arround of the news sequence with minimal processing. 1.

Planar Preprocessing for Spring Embedders

by J. Joseph Fowler, Stephen G. Kobourov
"... Abstract. Spring embedders are conceptually simple and produce straight-line drawings with an undeniable aesthetic appeal, which explains their prevalence when it comes to automated graph drawing. However, when drawing planar graphs, spring embedders often produce non-plane drawings, as edge crossin ..."
Abstract - Add to MetaCart
crossings do not factor into the objective function being minimized. On the other hand, there are fairly straight-forward algorithms for creating plane straight-line drawings for planar graphs, but the resulting layouts generally are not aesthetically pleasing, as vertices are often grouped in small regions
Results 1 - 10 of 724